Watch more of .local London 2026 → https://www.youtube.com/playlist?list=PL4RCxklHWZ9tH01MTlChYwUqN8Cm2tl2r Speakers: Afi Gbadago, Senior Developer Advocate, MongoDB You'll need your laptop to fully participate in this hands-on session. AI agents need memory to maintain context across sessions, learn from experience, and handle long-running tasks. The challenge? Deciding what to remember, where to store it, and how to retrieve it when it matters. In this workshop, you'll learn a practical framework for architecting memory systems that actually work in production. We'll cover: · Types of memory in agentic systems · Storage patterns: Where to persist memories and how to structure them for retrieval · Retrieval strategies: Combining vector search with metadata, recency, and other signals · Memory lifecycle: When to create, update, or prune memories to keep your system performant You'll apply this framework by building memory into an AI agent and seeing how different design choices impact behavior. 00:00:00 - Introduction & Workshop Overview 00:00:40 - The GenAI Value Problem: Why AI Systems Fail 00:01:40 - Stateless vs. Stateful: Why AI Agents Need Memory 00:02:43 - Accessing the Jupyter Notebook Lab Space 00:03:32 - Framing AI Memory Around Human Cognition 00:04:09 - Deep Dive: Short-Term Memory & Session History 00:04:23 - Deep Dive: Semantic, Procedural, & Episodic Long-Term Memory 00:04:49 - Working Memory & The LLM Scratchpad Explained 00:05:33 - Lab Exercise 1: Setting Up MongoDB Collections & Indexes 00:05:58 - CRUD Principles Applied to AI Memory Systems 00:06:23 - Designing & Extracting Memory Traces 00:07:12 - Data Modeling for AI Memories in JSON/BSON 00:07:56 - Retrieval Strategies: Text Search vs. Vector Search 00:08:45 - Implementing Auto-Embeddings on MongoDB Atlas 00:08:59 - Maximizing Accuracy with Hybrid Search 00:09:11 - Leveraging Aggregation Pipelines for Multi-Stage Retrieval 00:09:35 - Updating Memory: Overwriting vs. Temporal Versioning 00:09:59 - Deleting Memory: TTL Indexes & Performance Pruning 00:10:44 - Coding a Gemini-Powered AI Assistant Function Subscribe to the MongoDB for Developers YouTube Channel: https://www.youtube.com/@MongoDBDevelopers?sub_confirmation=1 Sign-up for a free cluster → https://www.mongodb.com/cloud/atlas/register Subscribe to MongoDB YouTube→ https://mdb.link/subscribe Visit Mongodb.com → https://mdb.link/MongoDB Read the MongoDB Blog → https://mdb.link/Blog Read the Developer Blog → https://mdb.link/developerblog MongoDB for Developers YouTube Channel → https://www.youtube.com/@MongoDBDevelopersSubscribe to the MongoDB for Developers YouTube Channel: https://www.youtube.com/@MongoDBDevelopers?sub_confirmation=1

 227      5